AI RESEARCH
SlowBA: An efficiency backdoor attack towards VLM-based GUI agents
arXiv CS.CL
•
ArXi:2603.08316v1 Announce Type: cross Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security mainly focuses on manipulating action correctness, the security risks related to response efficiency remain largely unexplored. In this paper, we